Wavelet-based fault detection and classification in MV grids using neural models: case study of Moroccan distribution system
-
,
Abstract
The increasing complexity of modern power distribution systems, driven by renewable integration, evolving load patterns, and aging infrastructure, has accentuated the need for advanced fault detection and classification mechanisms, particularly in emerging medium-voltage (MV) networks such as Moroccan distribution grid. However, traditional protection schemes, often based on centralized logic and fixed thresholds, tend to underperform in complex or high-impedance fault conditions. Furthermore, global signal features such as RMS or frequency components are insufficient to capture the localized and phase-dependent behavior of faults. These limitations have prompted a growing interest in intelligent, data-driven approaches combining signal processing and machine learning to achieve high-resolution fault diagnosis and improved system reliability. The present study proposes and evaluates an intelligent fault classification framework tailored to MV distribution networks. It explores the comparative performance of three neural architectures and supervised learning classifiers, Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Radial Basis Function Neural Network (RBFNN), applied to both globally extracted features and phase-localized wavelet descriptors. In addition to the baseline classification framework, a novel phase-based analysis method is introduced to enhance diagnostic performance. This method processes each phase and neutral current independently, based on the hypothesis that fault signatures emerge more distinctly when analysed separately. The experimental results demonstrate that neural models can reliably identify fault types across both approaches and underscores the potential of wavelet-enhanced AI models for smart and localized protection in emerging power distribution systems and prove its readiness for real-world deployment in SCADA-integrated protection systems.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The author states no conflict of interest.
-
Research funding: None declared.
-
Data availability: The datasets used in this study are available upon request. Interested researchers can contact me at [saadsarih@gmail.com] or [saad.sarih@edu.uiz.ac.ma] to obtain access to the data and results.
References
1. Wang, K, Qiu, X, Guo, S, Qi, F. Fault tolerance oriented sensors relay monitoring mechanism for overhead transmission line in smart grid. IEEE Sens J 2015;15:1982–91. https://doi.org/10.1109/JSEN.2014.2368559.Search in Google Scholar
2. Zargany, F, Shahbazian, M, Rad, HJ. Multi-sensor fault tolerant measurement based on tagaki–sugeno fuzzy model. Neural Comput Appl 2013;23:219–30. https://doi.org/10.1007/s00521-012-1328-0.Search in Google Scholar
3. Masri, A, Al-Jabi, M. Toward fault tolerant modelling for SCADA based electricity distribution networks, machine learning approach. PeerJ Comput Sci 2021;7:e554. https://doi.org/10.7717/peerj-cs.554.Search in Google Scholar PubMed PubMed Central
4. Zhang, F, Longhua, M. A fault detection method of microgrids with grid-connected inverter interfaced distributed generators based on the PQ control strategy. IEEE Trans Smart Grid 2019;10:4816–26. https://doi.org/10.1109/TSG.2018.2868967.Search in Google Scholar
5. Alenezi, M, Anayi, F, Packianather, M, Shouran, M. A hybrid machine learning framework for early fault detection in power transformers using PSO and DMO algorithms. Energies 2025;18:2024. https://doi.org/10.3390/en18082024.Search in Google Scholar
6. Bhuiyan, EA, Akhand, MA, Rahman Fahim, S, Sarker, SK, Das, SK. A deep learning through DBN enabled transmission line fault transient classification framework for multimachine microgrid systems. In: Cheong Sou, K, editor. International Transactions on Electrical Energy Systems 2022. Hoboken, NJ: John Wiley & Sons Ltd; 2022:1–12 pp.10.1155/2022/6820319Search in Google Scholar
7. Ponukumati, BK, Sinha, P, Maharana, MK, Kumar, AVP, Karthik, A. An intelligent fault detection and classification scheme for distribution lines using machine learning. Eng Technol Appl Sci Res 2022;12:8972–7. https://doi.org/10.48084/etasr.5107.Search in Google Scholar
8. Sarih, S, Boulghasoul, Z, Elbacha, A, Tajer, A, Chabaa, S. Intelligent control of the dynamic voltage restorer for fault ride through capability enhancement of a grid-connected photovoltaic power plant in accordance with recent Moroccan grid code. Recent Adv Electr Electron Eng 2023:2352–0973. https://doi.org/10.2174/0123520965259924231115101853.Search in Google Scholar
9. Mohapatra, H, Rath, AK. A fault tolerant routing scheme for advanced metering infrastructure: an approach towards smart grid. Clust Comput 2021;24:2193–211. https://doi.org/10.1007/s10586-021-03255-x.Search in Google Scholar
10. Amin, AA, Hasan, KM. A review of fault tolerant control systems: advancements and applications. Measurement 2019;143:58–68. https://doi.org/10.1016/j.measurement.2019.04.083.Search in Google Scholar
11. Chhetija, D, Rather, Z, Suryanarayana, D. A communication-free fault detection and classification scheme for power Islands. IEEE Transactions Ind Appl PP 2024:1–13. https://doi.org/10.1109/TIA.2024.3353722.Search in Google Scholar
12. Heo, S, Lee, J. Fault detection and classification using artificial neural networks. IFAC-PapersOnLine 2018;51:470–5. https://doi.org/10.1016/j.ifacol.2018.09.380.Search in Google Scholar
13. Assadi, K, Slimane, JB, Chalandi, H, Salhi, S. Shunt faults detection and classification in electrical power transmission line systems based on artificial neural networks. COMPEL – Int J Comput Math Electr Electron Eng 2023;42. https://doi.org/10.1108/COMPEL-10-2022-0371.Search in Google Scholar
14. Rai, P, Londhe, N, Raj, R. Fault classification in power system distribution network integrated with distributed generators using CNN. Elec Power Syst Res 2020;192. https://doi.org/10.1016/j.epsr.2020.106914.Search in Google Scholar
15. Silva, KM, Souza, BA, Brito, NSD. Fault detection and classification in transmission lines based on wavelet transform and ANN. IEEE Trans Power Deliv 2006;21:2058–63. https://doi.org/10.1109/TPWRD.2006.876659.Search in Google Scholar
16. LeCun, Y, Bengio, Y, Hinton, G. Deep learning. Nature 2015;521:436–44. https://doi.org/10.1038/nature14539.Search in Google Scholar PubMed
17. Sahu, BK, Panda, SK, Ghosh, A. Fault classification and localization in smart grids using a hybrid ANN-WT model. J Electr Eng Technol 2022;17:1007–18. https://doi.org/10.1007/s42835-021-00820-6.Search in Google Scholar
18. Muhammad, UJ, Aminu, II, Mahmoud, IA, Aliyu, UU, Usman, AG, Jibril, MM, et al.. An improved prediction of high-performance concrete compressive strength using ensemble models and neural networks. AI Civ Eng 2024;3:21. https://doi.org/10.1007/s43503-024-00040-8.Search in Google Scholar
19. Sakovich, N, Aksenov, D, Pleshakova, E, Gataullin, S. Wavelet-based optimization and numerical computing for fault detection method–signal fault localization and classification algorithm. Algorithms 2025;18:217. https://doi.org/10.3390/a18040217.Search in Google Scholar
20. Jamil, M, Khan, MA, Sharma, S, Song, X, Wu, H. Intelligent fault detection techniques in power distribution networks: a review. Elec Power Syst Res 2021;195:107135. https://doi.org/10.1016/j.epsr.2021.107135.Search in Google Scholar
21. Xu, Y, Bai, Z, Chen, M. Incipient fault detection based on feature adaptive ensemble net. Processes 2025;13:1474. https://doi.org/10.3390/pr13051474.Search in Google Scholar
22. Zhao, Q, Wang, B, Zhou, G, Zhang, W, Guan, X, Feng, W. An improved fault diagnosis approach based on support vector machine. In: IEEE International Conference on Prognostics and Health Management. Ottawa, ON: IEEE; 2016.10.1109/ICPHM.2016.7542827Search in Google Scholar
23. Costa, LHS, Santos, RBN, Costa, LDC, Mendes, VB, de Lima, NJB. A machine learning-based method for fault location in power distribution systems using transient analysis. PowerTech and 2020 EEEIC conferences. Madrid: IEEE; 2021.Search in Google Scholar
24. Benali, M, Lakssir, A, Elkounti, Y, Ouazzani, J. Fault location in distribution networks based on synchrophasor measurements and hybrid artificial intelligence: a comparison study. In: 2022 IEEE 22nd International Conference on Environment and Electrical Engineering and 6th Industrial and Commercial Power Systems Europe (EEEIC/ICPSEurope); 2022.Search in Google Scholar
25. D’Urso, D, Di Pasquale, E, Inza, SR, Cennamo, F. A novel real-time multi-fault location approach for low voltage grids. IEEE Trans Instrum Meas 2024;73. https://doi.org/10.1109/TIM.2024.3460879. Art. no. 9005011Search in Google Scholar PubMed
26. Ahmed, ABHM, Hassan, AH, El-Ghanam, SEA, Elkholy, MM, Omar, HIMZ. A novel fault detection and classification method for radial distribution networks based on artificial neural network. In: 2021 IEEE 21st International Conference on Environment and Electrical Engineering and 5th Industrial and Commercial Power Systems Europe (EEEIC/ICPSEurope conference). Bari: IEEE; 2021.Search in Google Scholar
27. Benali, M, Lakssir, A, Elkounti, Y, Ouazzani, J. An efficient algorithm for fault location in complex distribution networks based on synchronized measurements and hybrid artificial intelligence. In: 2021 IEEE 21st International Conference on Environment and Electrical Engineering and 5th Industrial and Commercial Power Systems Europe (EEEIC/ICPSEurope conference). Bari: IEEE; 2021.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
